作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2019, Vol. 45 ›› Issue (2): 315-320. doi: 10.19678/j.issn.1000-3428.0049372

• 开发研究与工程应用 • 上一篇    

结合表面纹理与断裂轮廓的碎片拼接方法

王飘,耿国华,杨稳,任健   

  1. 西北大学 信息科学与技术学院,西安 710127
  • 收稿日期:2017-11-21 出版日期:2019-02-15 发布日期:2019-02-15
  • 作者简介:王飘(1992—),女,硕士研究生,主研方向为图像处理、可视化技术;耿国华(通信作者),教授、博士生导师;杨稳、任健,硕士研究生。
  • 基金资助:

    国家自然科学基金重点项目(61731015);国家自然科学基金面上项目(61673319,61373117);国家自然科学基金青年基金(61602380);西北大学2017研究生自主创新项目(YZZ17182)。

Fragment Splicing Method Combined with Surface Texture and Fracture Contour

WANG Piao,GENG Guohua,YANG Wen,REN Jian   

  1. School of Information Science and Technology,Northwest University,Xi’an 710127,China
  • Received:2017-11-21 Online:2019-02-15 Published:2019-02-15

摘要:

陶土制文物在自然环境及人为发掘等过程中,碎片易受损缺失,断裂部位难以保证完整性,传统采用几何驱动的拼接方法受到限制。为此,针对断裂部位几何信息缺失的陶制文物碎片,提出一种结合表面几何纹理及断裂轮廓的拼接方法。使用Splatting lines生成方法提取碎片纹理特征线,对三维模型密集点采样,用不同参数溅射渲染2个深度图像,由两图像间差值生成线图。计算纹理形状边角信息,构造破损纹理约束条件,完成初步匹配。对断裂边界轮廓上的离散点集,利用遗传算法计算匹配点对,得到最终结果。实验结果表明,该方法能够实现缺损文物碎片的拼接,匹配度稳定在0.53以上,且对纹理特征显著及缺损严重的碎片拼接效果较优。

关键词: 碎片拼接, 纹理特征, 遗传算法, 轮廓匹配, 两两匹配, 多特征约束

Abstract:

In the process of natural environment and artificial excavation of pottery relics,the fragments are easy to be damaged and missing,and the integrity of the fracture site is difficult to be guaranteed.The traditional geometric driven splicing method is restricted.Aiming at the pottery relic fragments with missing geometric information,a splicing method combined with surface texture and fracture contour is proposed.Splatting lines method is used to extract the fragment texture feature lines,sampling the dense points of the 3D model,sputter two depth images with different parameters,and generate the graph by the difference between the two images.The edge and angle information of texture shape is calculated,and the constraint condition of damaged texture is constructed,and the initial matching is completed.For the discrete point set on the fracture boundary contour,the matching point pair is calculated by genetic algorithm,and the final result is obtained.Experimental results show that this method can realize the splicing of defective cultural relics fragments,and the matching degree is above 0.53,and the splicing effect of fragments with obvious texture feature and serious defects is better.

Key words: fragment splicing, texture feature, genetic algorithm, contour matching, pairwise matching, multi-characteristic constraints

中图分类号: